Language models have already evolved to do much more than language tasks, principally in the domain of image, audio, and soon video. Join Mostafa Dehghani to explore the emergent frontier of multimodal generation, what Gemini’s world knowledge unlocks that domain specific models cannot create, and how developers should be thinking about AI as a next-generation creative partner.
talk-data.com
K
Speaker
Kaushik Shivakumar
1
talks
Research Engineer
Google DeepMind
Filter by Event / Source
Talks & appearances
1 activities · Newest first